{"ID":2832081,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.06933","arxiv_id":"2512.06933","title":"TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding","abstract":"Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespread \"blind signing\" (approving transactions without understanding them). Through interviews with 16 Web3 users, we find that effective explanations should be structured, risk-aware, and grounded at the token-flow level. Motivated by these findings, we formulate TxSum, a new user-centered NLP task for Ethereum transaction understanding, and construct a dataset of 187 complex Ethereum transactions annotated with transaction-level summaries and token flow-level semantic labels. We further introduce MATEX, a grounded multi-agent framework for high-stakes transaction explanation. It selectively retrieves external knowledge under uncertainty and audits explanations against raw traces to improve token-flow-level factual consistency. MATEX achieves the strongest overall explanation quality, especially on micro-level factuality and intent quality. It improves user comprehension on complex transactions from 52.9% to 76.5% over the strongest baseline and raises malicious-transaction rejection from 36.0% to 88.0%, while maintaining a low false-rejection rate on benign transactions.","short_abstract":"Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespread \"blind signing\" (approving transactions without understanding them). Through interviews with 16 Web3 users, we find that effective explan...","url_abs":"https://arxiv.org/abs/2512.06933","url_pdf":"https://arxiv.org/pdf/2512.06933v3","authors":"[\"Zifan Peng\",\"Jingyi Zheng\",\"Yule Liu\",\"Huaiyu Jia\",\"Qiming Ye\",\"Jingyu Liu\",\"Xufeng Yang\",\"Mingchen Li\",\"Qingyuan Gong\",\"Xuechao Wang\",\"Xinlei He\"]","published":"2025-12-07T17:23:55Z","proceeding":"cs.CE","tasks":"[\"cs.CE\",\"cs.CL\",\"cs.HC\"]","methods":"[]","has_code":false}